codewithpurav's picture
First Push
599b413 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4267435371875763,
"min": 0.40171724557876587,
"max": 1.4423375129699707,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12809.1337890625,
"min": 12038.662109375,
"max": 43754.75,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989997.0,
"min": 29952.0,
"max": 989997.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989997.0,
"min": 29952.0,
"max": 989997.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6599948406219482,
"min": -0.10547038167715073,
"max": 0.6599948406219482,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 189.41851806640625,
"min": -25.41836166381836,
"max": 189.41851806640625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.005458198022097349,
"min": -0.03380587324500084,
"max": 0.6170322299003601,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.5665028095245361,
"min": -9.431838989257812,
"max": 146.23663330078125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06929687746876789,
"min": 0.06584537523921419,
"max": 0.07416517644347563,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9701562845627505,
"min": 0.49162961000405336,
"max": 1.1124776466521344,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015869734659064622,
"min": 0.00017189265751464214,
"max": 0.017727720663731156,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2221762852269047,
"min": 0.0022346045476903478,
"max": 0.2530226709495764,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.601176037735714e-06,
"min": 7.601176037735714e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010641646452829999,
"min": 0.00010641646452829999,
"max": 0.0033827729724091,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253369285714287,
"min": 0.10253369285714287,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354717000000001,
"min": 1.3886848,
"max": 2.5275909,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002631159164285714,
"min": 0.0002631159164285714,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00368362283,
"min": 0.00368362283,
"max": 0.11278633090999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010813434608280659,
"min": 0.010813434608280659,
"max": 0.8351534008979797,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15138807892799377,
"min": 0.15138807892799377,
"max": 5.846073627471924,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 318.07142857142856,
"min": 271.23148148148147,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31171.0,
"min": 15984.0,
"max": 33407.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6606968942376756,
"min": -1.0000000521540642,
"max": 1.725300956264283,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 161.08759874105453,
"min": -30.995801597833633,
"max": 184.706398665905,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6606968942376756,
"min": -1.0000000521540642,
"max": 1.725300956264283,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 161.08759874105453,
"min": -30.995801597833633,
"max": 184.706398665905,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03554626219316635,
"min": 0.032754109242415765,
"max": 18.048041390255094,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.4479874327371363,
"min": 3.4479874327371363,
"max": 288.7686622440815,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750488178",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750490324"
},
"total": 2146.578610676,
"count": 1,
"self": 0.5256249020003452,
"children": {
"run_training.setup": {
"total": 0.020298447999721247,
"count": 1,
"self": 0.020298447999721247
},
"TrainerController.start_learning": {
"total": 2146.032687326,
"count": 1,
"self": 1.2551042799864263,
"children": {
"TrainerController._reset_env": {
"total": 2.2853289619997668,
"count": 1,
"self": 2.2853289619997668
},
"TrainerController.advance": {
"total": 2142.4185025550137,
"count": 64033,
"self": 1.3152170170178579,
"children": {
"env_step": {
"total": 1498.2698859380516,
"count": 64033,
"self": 1359.794847289279,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.7418130348624,
"count": 64033,
"self": 4.411150745893337,
"children": {
"TorchPolicy.evaluate": {
"total": 133.33066228896905,
"count": 62541,
"self": 133.33066228896905
}
}
},
"workers": {
"total": 0.7332256139102356,
"count": 64033,
"self": 0.0,
"children": {
"worker_root": {
"total": 2141.486415166763,
"count": 64033,
"is_parallel": true,
"self": 887.3292644227922,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017915670000547834,
"count": 1,
"is_parallel": true,
"self": 0.0005674180006280949,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012241489994266885,
"count": 8,
"is_parallel": true,
"self": 0.0012241489994266885
}
}
},
"UnityEnvironment.step": {
"total": 0.05085801799987166,
"count": 1,
"is_parallel": true,
"self": 0.0005652639993058983,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044137500026408816,
"count": 1,
"is_parallel": true,
"self": 0.00044137500026408816
},
"communicator.exchange": {
"total": 0.04826949900007094,
"count": 1,
"is_parallel": true,
"self": 0.04826949900007094
},
"steps_from_proto": {
"total": 0.0015818800002307398,
"count": 1,
"is_parallel": true,
"self": 0.0003304509991721716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012514290010585682,
"count": 8,
"is_parallel": true,
"self": 0.0012514290010585682
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1254.1571507439708,
"count": 64032,
"is_parallel": true,
"self": 30.571036580980035,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.644707914954324,
"count": 64032,
"is_parallel": true,
"self": 21.644707914954324
},
"communicator.exchange": {
"total": 1111.3815978250332,
"count": 64032,
"is_parallel": true,
"self": 1111.3815978250332
},
"steps_from_proto": {
"total": 90.55980842300323,
"count": 64032,
"is_parallel": true,
"self": 17.570085766246393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 72.98972265675684,
"count": 512256,
"is_parallel": true,
"self": 72.98972265675684
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 642.8333995999442,
"count": 64033,
"self": 2.4842420900049547,
"children": {
"process_trajectory": {
"total": 123.27896513393625,
"count": 64033,
"self": 122.97766661693686,
"children": {
"RLTrainer._checkpoint": {
"total": 0.30129851699939536,
"count": 2,
"self": 0.30129851699939536
}
}
},
"_update_policy": {
"total": 517.070192376003,
"count": 450,
"self": 288.07693138805826,
"children": {
"TorchPPOOptimizer.update": {
"total": 228.99326098794472,
"count": 22779,
"self": 228.99326098794472
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.950002327561378e-07,
"count": 1,
"self": 7.950002327561378e-07
},
"TrainerController._save_models": {
"total": 0.07375073399998655,
"count": 1,
"self": 0.0012359370002741343,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07251479699971242,
"count": 1,
"self": 0.07251479699971242
}
}
}
}
}
}
}